A permutation test is a non-parametric statistical method for hypothesis testing. It is based on repeated random rearrangement (permutation) of observed data to determine the probability of the observed result under the null hypothesis. Permutation tests are particularly useful when sample sizes are small or when the assumptions for parametric tests are not met.

Typical software functions in the area of "Permutation Test":

- Data Import: Reading and preparing the data to be analyzed.
- Test Statistic Calculation: Computation of the relevant test statistic for the original data.
- Permutation Generation: Creation of random permutations of the data.
- Monte Carlo Simulation: Performing a large number of permutations to approximate the distribution.
- P-value Calculation: Determination of the p-value based on the distribution of permuted test statistics.
- Visualization: Graphical representation of results, e.g., as a histogram of permuted test statistics.
- Result Export: Output of test results in various formats.

Examples of "Permutation Test":

- Mean Comparison: Testing for differences between two independent groups.
- Correlation Analysis: Checking the significance of correlations between variables.
- Regression Analysis: Testing the significance of regression coefficients.
- Analysis of Variance (ANOVA): Comparison of means across multiple groups.
- Time Series Analysis: Testing for differences in time series patterns.
- Cluster Analysis: Verifying the significance of cluster solutions.

Utilization analysis according to loss classes